Reconciling solar forecasts: Probabilistic forecasting with homoscedastic Gaussian errors on a geographical hierarchy

Abstract Hierarchical forecasting and reconciliation are new to the field of solar engineering. Previous papers in this series, namely, Yang et al. (2017a, 2017b), and Yagli et al. (2019b), discussed various reconciliation techniques for deterministic solar forecasts obtained across spatio-temporal hierarchies. This paper extends the discussion into probability space, and studies how reconciliation can affect the performance of probabilistic forecasting. More specifically, qualities of the parametric predictive distributions before and after reconciliation are compared. Four minimum-trace-based reconciliation techniques are used to reconcile day-ahead and hour-ahead forecasts generated using two datasets: (1) distributed solar power generation for 318 simulated PV systems in California, and (2) satellite-derived irradiance over Arizona. The empirical result shows that reconciliation not only improves the accuracy of point forecasts, but also leads to high-quality predictive distributions in terms of sharpness, calibration, and skill score. Moreover, such improvement is quite general, and does not seem to depend on data, hierarchy structure, nor the underlying forecasting model.

[1]  Jan Kleissl,et al.  Operational solar forecasting for the real-time market , 2019, International Journal of Forecasting.

[2]  Dazhi Yang,et al.  Kriging for NSRDB PSM version 3 satellite-derived solar irradiance , 2018, Solar Energy.

[3]  Gokhan Mert Yagli,et al.  Ensemble kriging for environmental spatial processes , 2019, 2019 IEEE International Conference on Big Data (Big Data).

[4]  Dipti Srinivasan,et al.  Reconciling solar forecasts: Sequential reconciliation , 2019, Solar Energy.

[5]  Qun Zhou,et al.  Coherent Probabilistic Solar Power Forecasting , 2018, 2018 IEEE International Conference on Probabilistic Methods Applied to Power Systems (PMAPS).

[6]  Carlos D. Rodriguez-Gallegos,et al.  Reconciling solar forecasts: Temporal hierarchy , 2017 .

[7]  Galen Maclaurin,et al.  The National Solar Radiation Data Base (NSRDB) , 2017, Renewable and Sustainable Energy Reviews.

[8]  Dazhi Yang,et al.  Post-processing of NWP forecasts using ground or satellite-derived data through kernel conditional density estimation , 2019, Journal of Renewable and Sustainable Energy.

[9]  Dazhi Yang,et al.  Very short term irradiance forecasting using the lasso , 2015 .

[10]  J. Kleissl,et al.  Reporting of irradiance modeling relative prediction errors , 2013 .

[11]  Richard Perez,et al.  Can we gauge forecasts using satellite-derived solar irradiance? , 2019, Journal of Renewable and Sustainable Energy.

[12]  Hans-Georg Beyer,et al.  Irradiance Forecasting for the Power Prediction of Grid-Connected Photovoltaic Systems , 2009, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[13]  Dazhi Yang,et al.  Making reference solar forecasts with climatology, persistence, and their optimal convex combination , 2019, Solar Energy.

[14]  Joakim Widén,et al.  Review on probabilistic forecasting of photovoltaic power production and electricity consumption , 2018 .

[15]  J. Kleissl,et al.  Intra-hour forecasting with a total sky imager at the UC San Diego solar energy testbed , 2011 .

[16]  Nan Chen,et al.  Solar irradiance forecasting using spatial-temporal covariance structures and time-forward kriging , 2013 .

[17]  Abbas Khosravi,et al.  A Survey of Computational Intelligence Techniques for Wind Power Uncertainty Quantification in Smart Grids , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[18]  Charles F. Manski,et al.  Comparing the Point Predictions and Subjective Probability Distributions of Professional Forecasters , 2006 .

[19]  Dipti Srinivasan,et al.  Automatic hourly solar forecasting using machine learning models , 2019, Renewable and Sustainable Energy Reviews.

[20]  Fotios Petropoulos,et al.  Forecasting with temporal hierarchies , 2017, Eur. J. Oper. Res..

[21]  Stefano Alessandrini,et al.  An ultra-fast way of searching weather analogs for renewable energy forecasting , 2019, Solar Energy.

[22]  Mathieu David,et al.  Comparison of intraday probabilistic forecasting of solar irradiance using only endogenous data , 2018, International Journal of Forecasting.

[23]  Rob J. Hyndman,et al.  Optimal combination forecasts for hierarchical time series , 2011, Comput. Stat. Data Anal..

[24]  Dazhi Yang,et al.  Ultra-fast preselection in lasso-type spatio-temporal solar forecasting problems , 2018, Solar Energy.

[25]  Dazhi Yang,et al.  A correct validation of the National Solar Radiation Data Base (NSRDB) , 2018, Renewable and Sustainable Energy Reviews.

[26]  Tilmann Gneiting,et al.  Of quantiles and expectiles: consistent scoring functions, Choquet representations and forecast rankings , 2015, 1503.08195.

[27]  Dazhi Yang,et al.  OpenSolar: Promoting the openness and accessibility of diverse public solar datasets , 2019, Solar Energy.

[28]  A. Raftery,et al.  Probabilistic forecasts, calibration and sharpness , 2007 .

[29]  Pierre Pinson,et al.  Very Short-Term Nonparametric Probabilistic Forecasting of Renewable Energy Generation— With Application to Solar Energy , 2016, IEEE Transactions on Power Systems.

[30]  Ralf Mikut,et al.  On the use of probabilistic forecasts in scheduling of renewable energy sources coupled to storages , 2018 .

[31]  Dazhi Yang,et al.  Spatial prediction using kriging ensemble , 2018, Solar Energy.

[32]  Abbas Khosravi,et al.  Uncertainty handling using neural network-based prediction intervals for electrical load forecasting , 2014 .

[33]  Dazhi Yang,et al.  Ensemble model output statistics as a probabilistic site-adaptation tool for satellite-derived and reanalysis solar irradiance , 2020 .

[34]  T. Gneiting Making and Evaluating Point Forecasts , 2009, 0912.0902.

[35]  Dazhi Yang,et al.  Reconciling solar forecasts: Geographical hierarchy , 2017 .

[36]  Rob J. Hyndman,et al.  Optimal Forecast Reconciliation for Hierarchical and Grouped Time Series Through Trace Minimization , 2018, Journal of the American Statistical Association.

[37]  Jan Kleissl,et al.  Editorial: Submission of Data Article is now open , 2018, Solar Energy.

[38]  Dazhi Yang,et al.  A universal benchmarking method for probabilistic solar irradiance forecasting , 2019, Solar Energy.

[39]  George Athanasopoulos,et al.  Hierarchical forecasts for Australian domestic tourism , 2009 .

[40]  Dazhi Yang,et al.  A guideline to solar forecasting research practice: Reproducible, operational, probabilistic or physically-based, ensemble, and skill (ROPES) , 2019, Journal of Renewable and Sustainable Energy.

[41]  Dazhi Yang,et al.  Ultra-fast analog ensemble using kd-tree , 2019, Journal of Renewable and Sustainable Energy.

[42]  Rob J. Hyndman,et al.  Forecasting Uncertainty in Electricity Smart Meter Data by Boosting Additive Quantile Regression , 2016, IEEE Transactions on Smart Grid.